© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128409
    Prev
    Next
    INDEX
    Explanations

    numbers and create

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (digits and decimal numbers), i.e. it detects numeric quantities in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    趿
    -2.41
    %;
    -2.31
    {
    -2.30
    ";
    -2.25
    GIVEREF
    -2.20
     ois
    -2.16
    ḿ
    -2.14
     minuter
    -2.06
    憮
    -2.03
    脔
    -2.03
    POSITIVE LOGITS
     or
    2.88
    6
    2.38
     in
    2.17
    7
    2.17
     even
    2.14
    1
    2.11
    2
    2.08
    0
    2.06
     create
    2.00
    Kelebihan
    1.99
    Activations Density 0.065%

    No Known Activations